CN109394203A - The monitoring of phrenoblabia convalescence mood and interference method - Google Patents
The monitoring of phrenoblabia convalescence mood and interference method Download PDFInfo
- Publication number
- CN109394203A CN109394203A CN201710710278.1A CN201710710278A CN109394203A CN 109394203 A CN109394203 A CN 109394203A CN 201710710278 A CN201710710278 A CN 201710710278A CN 109394203 A CN109394203 A CN 109394203A
- Authority
- CN
- China
- Prior art keywords
- voice signal
- intelligent terminal
- mood
- signal
- electrocardiosignal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000036651 mood Effects 0.000 title claims abstract description 103
- 238000000034 method Methods 0.000 title claims abstract description 59
- 208000034657 Convalescence Diseases 0.000 title claims abstract description 58
- 238000012544 monitoring process Methods 0.000 title claims abstract description 58
- 230000002996 emotional effect Effects 0.000 claims abstract description 74
- 230000008451 emotion Effects 0.000 claims abstract description 61
- 238000002567 electromyography Methods 0.000 claims abstract description 52
- 230000004936 stimulating effect Effects 0.000 claims abstract description 24
- 239000000284 extract Substances 0.000 claims abstract description 21
- 238000004891 communication Methods 0.000 claims description 20
- 238000000605 extraction Methods 0.000 claims description 19
- 238000012549 training Methods 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 15
- 230000003183 myoelectrical effect Effects 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 11
- 238000004458 analytical method Methods 0.000 claims description 8
- 230000002123 temporal effect Effects 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 238000011002 quantification Methods 0.000 claims description 5
- 230000005236 sound signal Effects 0.000 claims description 4
- 238000013461 design Methods 0.000 claims description 3
- 238000001228 spectrum Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 2
- 230000000875 corresponding effect Effects 0.000 claims 5
- 230000002596 correlated effect Effects 0.000 claims 1
- 230000002452 interceptive effect Effects 0.000 description 20
- 238000010586 diagram Methods 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 8
- 230000036541 health Effects 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 7
- 230000001771 impaired effect Effects 0.000 description 7
- 230000002159 abnormal effect Effects 0.000 description 6
- 238000004020 luminiscence type Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 238000013139 quantization Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 3
- 238000012797 qualification Methods 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 229910021417 amorphous silicon Inorganic materials 0.000 description 2
- 210000001367 artery Anatomy 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 239000010408 film Substances 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 210000003462 vein Anatomy 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 238000001159 Fisher's combined probability test Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 239000012528 membrane Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000000638 stimulation Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 239000010409 thin film Substances 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/389—Electromyography [EMG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6802—Sensor mounted on worn items
- A61B5/681—Wristwatch-type devices
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
- A61N1/00—Electrotherapy; Circuits therefor
- A61N1/18—Applying electric currents by contact electrodes
- A61N1/32—Applying electric currents by contact electrodes alternating or intermittent currents
- A61N1/36—Applying electric currents by contact electrodes alternating or intermittent currents for stimulation
- A61N1/36014—External stimulators, e.g. with patch electrodes
- A61N1/36025—External stimulators, e.g. with patch electrodes for treating a mental or cerebral condition
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Animal Behavior & Ethology (AREA)
- Biophysics (AREA)
- Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Surgery (AREA)
- Molecular Biology (AREA)
- Medical Informatics (AREA)
- Psychiatry (AREA)
- Artificial Intelligence (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Social Psychology (AREA)
- Psychology (AREA)
- Hospice & Palliative Care (AREA)
- Child & Adolescent Psychology (AREA)
- Developmental Disabilities (AREA)
- Educational Technology (AREA)
- Mathematical Physics (AREA)
- Fuzzy Systems (AREA)
- Evolutionary Computation (AREA)
- Neurology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Cardiology (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a kind of monitoring of phrenoblabia convalescence mood and interference methods.This method comprises the following steps: acquisition electrocardiosignal, electromyography signal, voice signal；Electrocardiosignal, electromyography signal are transferred to intelligent terminal, and intelligent terminal carries out the pretreatment of electrocardiosignal and individual features value is extracted, the pretreatment of progress electromyography signal is extracted with individual features value, carry out the pretreatment of voice signal and individual features value is extracted；Mood associated eigenvalue is obtained by the individual features value of electrocardiosignal, the individual features value of electromyography signal, mood associated eigenvalue is compared with preset Emotion identification model, obtains real-time emotion state；When real-time emotion state is Positive emotion or Negative Emotional, generates primary return and record instruction, intelligent terminal extracts the corresponding voice messaging of voice signal and saved；When the real-time emotion state detected is Negative Emotional and the Negative Emotional is more than preset threshold, start microcurrent stimulating component operation.This method is easy to use.
Description
Technical field
The present invention relates to phrenoblabia rehabilitations, more particularly to a kind of monitoring of phrenoblabia convalescence mood and intervention side
Method.
Background technique
The rehabilitation course of convalescence patient with phychlogical problems includes two big core procedures --- mood monitoring and Emotional intervention.Mesh
Before depend on using measurement table (including emotional state behavior assessment, mood speciality assessment, motion management assessment etc.) carry out
Mood assessments, and pass through the Emotional intervention of the participation of medical staff and intervention completion patient.
The convalescent mood of phrenoblabia, which is tested and assessed and intervened, at this stage is all largely dependent upon health care professional, and one
Aspect is limited to the phrenoblabia specialty on rehabilitation medical care talent in short supply at present, leads to the convalescent motion management work of phrenoblabia
It can only be completed in Partial Hospitals, still there are a large amount of patients with phychlogical problems to cannot get corresponding motion management rehabilitation training, serious shadow
Ring the rehabilitation efficacy and quality of life of patient；On the other hand, it tests and assesses in existing motion management and is depended on the technical method intervened
The result of the personal experience of health care professional, motion management lack quantifiable index, cause existing motion management subjective
Property it is extremely strong, introduce many uncertain factors for entire motion management process.Meanwhile existing motion management technology, due to limited
In conditions such as personnel, equipment, it can only carry out in hospital, obtained related emotional management result is all on time and space
Discrete, and a kind of instinct of the mood as the mankind, it is not present in the life of people, also changes at any time all the time
A possibility that, and compared to hospital, the mood in daily life reflects that, closer to most true emotional status, these demands exist
It cannot achieve in existing motion management technology.
Summary of the invention
Based on this, it is necessary to provide it is a kind of may be implemented the mood based on multi-physiological-parameter and voice signal it is objective, quantization,
The phrenoblabia convalescence mood monitoring continuously monitored and interference method.
A kind of monitoring of phrenoblabia convalescence mood and interference method, include the following steps:
EGC sensor acquires the electrocardiosignal of patient with phychlogical problems, and myoelectric sensor acquires the myoelectricity of patient with phychlogical problems
Signal, voice collection assembly acquire the voice signal around patient with phychlogical problems；
Collected electrocardiosignal, electromyography signal are transferred to intelligent terminal, the intelligence by communication part by controller
Terminal carries out the pretreatment of electrocardiosignal and individual features value is extracted, the pretreatment of progress electromyography signal and individual features value mention
The pretreatment and individual features value for taking, carrying out voice signal are extracted；
The intelligent terminal obtains mood correlation by individual features value, the individual features value of electromyography signal of electrocardiosignal
The mood associated eigenvalue is compared with preset Emotion identification model for characteristic value, the intelligent terminal, obtains in real time
Emotional state；
The intelligent terminal generates primary return and records instruction, and the intelligent terminal extracts the corresponding voice messaging of voice signal simultaneously
It is saved；
When the real-time emotion state detected is Negative Emotional and the Negative Emotional is more than preset threshold, the intelligence
Energy terminal, which generates a microcurrent stimulating component enabled instruction and controls wearable bracelet by controller, starts micro-current thorn
Swash component operation, the microcurrent stimulating component output pulse current prompts patient with phychlogical problems；Wherein, pulse current
Intensity it is directly proportional to the intensity of Negative Emotional.
Detect the real-time emotion state in one of the embodiments, whether to judge the Negative Emotional after Negative Emotional
When more than preset threshold, specifically comprise the following steps:
The intelligent terminal, with after corresponding characteristics extraction, carries out classifier training in the pretreatment for completing voice signal
Identify that, to obtain the emotional state intensity of the real-time emotion state, the intelligent terminal judges the mood shape with classifier
Whether state intensity is more than preset threshold.
It obtains specifically comprising the following steps: when the real-time emotion state in one of the embodiments,
The intelligent terminal extracts, at the signal of electromyography signal in the signal processing and individual features value for completing electrocardiosignal
After reason and individual features value are extracted, pattern classification further is carried out to electrocardiosignal and electromyography signal, to obtain the real-time feelings
Not-ready status specifically includes:
1) the feature weight value of each individual features value is initialized；
2) weight that each dimensional characteristics are calculated by Relief algorithm eliminates the lesser feature of weighted value；
3) feature vector after selection is subjected to classified calculating using classifier；
4) classification results of the real-time emotion state are obtained.
The classifier training specifically includes in one of the embodiments: establishing the voice signal file presorted
Set, and voice signal each in the voice signal file set is extracted into characteristic parameter, by the feature of each voice signal
Parameter and the label presorted put together to form the feature vector of a tape label for classifier modules study, by all languages
The feature vector for the tape label that sound signal file is formed is put together, the set of eigenvectors of tape label is formed, by this feature vector
Collection is used as training data, is trained for classifier, generates the classifier trained；
The classifier identification specifically includes: after being successfully trained to classifier, voice signal to be sorted is defeated
Enter into characteristic parameter extraction module, generate corresponding set of eigenvectors, then this set of eigenvectors is input to point trained
In class device, the emotional state classification and corresponding emotional state intensity of the voice signal are generated.
The communication part is with bluetooth 5.0 for technical standard and by using 2Mbps in one of the embodiments,
PHY:HC1_LE_Set Default Phy Cmd indicates that controller starts PHY renewal process.
In one of the embodiments, further include following steps: the intelligent terminal to the electrocardiosignal received do as
Lower processing:
1) baseline drift, myoelectricity noise and the Hz noise of electrocardiosignal are removed by Butterworth filter, and are passed through
The output of the Butterworth filter returns again to, and inhibits phase distortion by the Butterworth filter gain；
2) characteristic point of electrocardiosignal is identified by Wavelet transformation；
It 3) include calculating when calculating the individual features value of electrocardiosignal: average value, standard deviation, first-order difference, normalization one
Order difference, second differnce, normalization second differnce, ecg-r wave wave crest, electrocardio P wave wave crest, electrocardio T wave wave crest, the interval P-Q, Q-
The interval S, the numerical value at the interval S-T, the first-order difference of adjacent P wave and T wave, QRS period, heart rate and heart rate variability numerical value.
In one of the embodiments, further include following steps: the intelligent terminal to the electromyography signal received do as
Lower processing:
1) after electromyography signal being amplified 2000-5000 times, ambient noise, motion artifacts, interior is removed by bandpass filter
Unstability generate noise；
2) electromyography signal is sampled with the sample frequency of 1kHz, obtains the discrete value of electromyography signal；
3) by the analysis window electromyography signal that is applied to that treated；
4) include calculating when calculating the individual features value of electromyography signal in each analysis window: mean value, zero passage number,
Mean-square value, three rank moment of the origns, quadravalence moment of the orign, the mean power of power spectrum and median frequency and Wigner distribution.
Voice signal in one of the embodiments, around the voice collection assembly acquisition patient with phychlogical problems is specific
Include the following steps:
The voice signal around patient with phychlogical problems is acquired in real time by voice collection assembly, and by institute collected
Predicate sound signal is transmitted to memory module and is saved, and the memory module saves the number of the voice signal of 30min length
According to amount, with the storage of new voice signal, the memory module deletes the data volume of the voice signal before 30min length.
The intelligent terminal extracts the corresponding voice messaging of voice signal and carries out preservation tool in one of the embodiments,
Body includes the following steps:
When the intelligent terminal completes the pretreatment of the electrocardiosignal and individual features value is extracted, completes the myoelectricity and believe
Number pretreatment and individual features value extract after, if the obtained real-time emotion state be Positive emotion or Negative Emotional,
The intelligent terminal generates primary time record instruction and is transmitted to communication part, the controller detection in the wearable bracelet
When receiving back record instruction to the communication part, by the data of the voice signal of 30min stored in the memory module
Amount is sent to the intelligent terminal through the communication part.
In one of the embodiments, further include following steps:
The intelligent terminal carries out the data volume of the voice signal after the data volume for receiving the voice signal
Processing, specifically includes:
1) the data volume pretreatment of the voice signal: including quantification treatment, preemphasis, sub-frame processing, windowing process；
2) it calculates voice mood characteristic value: voice letter serially being carried out to the data volume of the pretreated voice signal
Number processing, extract the temporal signatures of the data volume of the voice signal, fundamental frequency feature, voicing decision, word speed extract, formant
It extracts；Wherein, the temporal signatures include short-time energy, short-time zero-crossing rate, in short-term auto-correlation coefficient and short-time average magnitade difference function；
The fundamental frequency is characterized in calculating by mean amplitude of tide difference function method and Cepstrum Method；The voicing decision is classified by Fisher
Method is realized；The word speed is characterized in realizing by the voice split plot design of wavelet transformation；The extraction formant is by linear pre-
Compiling method is surveyed to realize.
Above-mentioned phrenoblabia convalescence mood monitoring and interference method, are utilized wearable technology, speech recognition technology
And machine learning techniques, the objective mood based on multi-physiological-parameter and voice signal, quantization, continuous monitoring may be implemented, and
Intervened when recognizing abnormal emotion, is conducive to record the most true emotional state of patient under daily life state, and
By intervening reduction in time or even eliminating patient with phychlogical problems's abnormal emotion to patient, other people and social bring harm.
Above-mentioned phrenoblabia convalescence mood monitoring and interference method, record patient's by wearable bracelet in real time
Electrocardiosignal, electromyography signal and voice messaging, collected electrocardiosignal, electromyography signal are transferred to intelligent terminal, lead to immediately
It crosses series of algorithms to extract to obtain mood associated eigenvalue and be compared with Emotion identification model, obtains real-time emotion state.
When real-time emotion state is Positive emotion or Negative Emotional, generate it is primary return record instruction, when the last period automatically extracted immediately
Between voice messaging saved.By above-mentioned phrenoblabia convalescence mood monitoring and interference method, spirit may be implemented
Mood real-time monitoring in impaired patients daily life obtains most guaranteeing mood close to the physiological signal under true emotional state
The reliability and accuracy in physiological signal source in identification.Meanwhile memory can be saved by returning record instruction, and be effectively recorded
The relevant voice messaging of mood provides accurately voice letter for further fining assessment emotional intensity and disease course analysis
Breath.
Above-mentioned phrenoblabia convalescence mood monitoring and interference method, wearable bracelet are separately integrated with microcurrent stimulating
Component, after the real-time Negative Emotional detected is more than preset threshold, microcurrent stimulating component can export pulse current, and pulse
The intensity of electric current is directly proportional to real-time Negative Emotional intensity, to prompt patient with phychlogical problems itself, helps its objective
The Negative Emotional of oneself is recognized on ground, early to carry out mood adjustment, utmostly reduce because of patient with phychlogical problems not and
When recognize the Negative Emotional of oneself or can not adjust oneself Negative Emotional and to oneself, other people, the harm of social bring.
Above-mentioned phrenoblabia convalescence mood monitoring and interference method realize that mood is supervised in real time by wearable bracelet
The timely intervention with Negative Emotional is surveyed, Traditional Spirit obstacle convalescence is overcome and needs health care professional's intervention that could complete feelings
Thread manages brought limitation, and more breaching previous patient with phychlogical problems only just can be carried out in related qualification hospital
Territory restriction brought by convalescence emotion management training allows more patients with phychlogical problems that can complete convalescent mood pipe
Reason training, promotes rehabilitation efficacy.
Above-mentioned phrenoblabia convalescence mood monitoring and interference method, record patient's by wearable bracelet in real time
Electrocardiosignal, electromyography signal and voice messaging, and handle to obtain mood associated eigenvalue by series of algorithms, for spirit barrier
Hinder the assessment of patient mood to introduce objective quantizating index, avoid the Subjective Factors of his evaluation table in Traditional measurements method,
It ensure that the coherence and continuity of mood assessments.Meanwhile mood assessments are after completing quantification of targets, can be each essence
Refreshing impaired patients establish the motion management database of itself, understand patient's health convenient for patient itself, family numbers of patients and medical staff
The whole process information of emotion management training in the multiple phase provides comprehensive and accurately data information for the adjustment of subsequent rehabilitation scheme.
With the continuous accumulation of related data, it will effectively improve through electrocardiosignal, electromyography signal and voice messaging and reflect spirit
The accuracy of impaired patients real-time emotion experience.
Detailed description of the invention
Fig. 1 is the monitoring of phrenoblabia convalescence mood and the interfering system general construction schematic diagram of an embodiment；
Fig. 2 is the wearable hand ring diagram of the monitoring and interfering system of phrenoblabia convalescence mood shown in Fig. 1；
Fig. 3 is the wearable bracelet functional structure frame of the monitoring and interfering system of phrenoblabia convalescence mood shown in Fig. 1
Figure；
Fig. 4 is the electrocardio sensing of the monitoring and the wearable bracelet of interfering system of phrenoblabia convalescence mood shown in Fig. 1
Device schematic diagram；
Fig. 5 is that the monitoring of phrenoblabia convalescence mood shown in Fig. 1 and the myoelectricity of the wearable bracelet of interfering system are simulated
Acquisition Circuit schematic diagram；
Fig. 6 is that the monitoring of phrenoblabia convalescence mood shown in Fig. 1 is located in advance with voice signal in the intelligent terminal of interfering system
Manage flow chart；
Fig. 7 is to calculate voice mood in the monitoring of phrenoblabia convalescence mood shown in Fig. 1 and the intelligent terminal of interfering system
The architecture diagram of characteristic value；
Fig. 8 is the monitoring of phrenoblabia convalescence mood shown in Fig. 1 and classification of speech signals in the intelligent terminal of interfering system
Device trains flow chart；
Fig. 9 is the monitoring of phrenoblabia convalescence mood shown in Fig. 1 and classification of speech signals in the intelligent terminal of interfering system
Device identification process figure；
Figure 10 is the power supply management of the monitoring and the wearable bracelet of interfering system of phrenoblabia convalescence mood shown in Fig. 1
Assembly principle figure.
Description of symbols
10, the monitoring of phrenoblabia convalescence mood and interfering system；100, wearable bracelet；110, bracelet main body；120,
Impedance piece；130, EGC sensor；140, myoelectric sensor；150, communication part；160, voice collection assembly；170, storage group
Part；180, microcurrent stimulating component；190, Power Supply Assembly；1100, switch block；1110, display screen；1120, controller；
1130, power supply management component；200, intelligent terminal.
Specific embodiment
To facilitate the understanding of the present invention, a more comprehensive description of the invention is given in the following sections with reference to the relevant attached drawings.In attached drawing
Give presently preferred embodiments of the present invention.But the invention can be realized in many different forms, however it is not limited to this paper institute
The embodiment of description.On the contrary, purpose of providing these embodiments is keeps the understanding to the disclosure more thorough
Comprehensively.
It should be noted that it can directly on the other element when element is referred to as " being fixed on " another element
Or there may also be elements placed in the middle.When an element is considered as " connection " another element, it, which can be, is directly connected to
To another element or it may be simultaneously present centering elements.
Unless otherwise defined, all technical and scientific terms used herein and belong to technical field of the invention
The normally understood meaning of technical staff is identical.Term as used herein in the specification of the present invention is intended merely to description tool
The purpose of the embodiment of body, it is not intended that in the limitation present invention.Term as used herein "and/or" includes one or more phases
Any and all combinations of the listed item of pass.
Shown in Figure 1, the present embodiment relates to a kind of monitoring of phrenoblabia convalescence mood and interfering system 10.The essence
Refreshing obstacle convalescence mood monitoring and interfering system 10 include wearable bracelet 100 and intelligent terminal 200.
Shown in Figure 2, above-mentioned wearable bracelet 100 has bracelet main body 110, impedance piece 120, EGC sensor
130, myoelectric sensor 140, voice collection assembly 160, communication part 150, storage assembly 170, microcurrent stimulating component 180,
Power Supply Assembly 190, switch block 1100, display screen 1110 and controller 1120.Communication part in the present embodiment can be
Bluetooth communication component 150.
EGC sensor 130, myoelectric sensor 140, impedance piece 120 and microcurrent stimulating component 180 are all connected to hand
In ring main body 110 with for respectively with the skin contact of patient with phychlogical problems；Power Supply Assembly 190, switch block 1100 and aobvious
Display screen 1110 is all connected on the outer wall of bracelet main body 110, and appearance is surrounded by between display screen 1110 and the outer wall of bracelet main body 110
Set chamber；Communication part 150, storage assembly 170, voice collection assembly 160 and controller 1120 are respectively positioned in accommodating cavity；
It is shown in Figure 3, controller 1120 and EGC sensor 130, myoelectric sensor 140, voice collection assembly 160,
Storage assembly 170, microcurrent stimulating component 180, switch block 1100 and display screen 1110 are electrically connected.
It is shown in Figure 4,130 schematic diagram of EGC sensor of wearable bracelet.
Controller 1120 is connect with intelligent terminal 200.
Intelligent terminal 200 is used to receive the electrocardiosignal and electromyography signal that the wearable transmission of bracelet 100 comes, and can be in the heart
Pattern classification is carried out after the pretreatment of electric signal and characteristics extraction, the pretreatment of electromyography signal and characteristics extraction, to obtain
The real-time emotion state of patient with phychlogical problems.When obtained real-time emotion state is Positive emotion or Negative Emotional, intelligence is eventually
End 200 generates primary return and records the wearable bracelet of instruction notification for the stored voice signal of storage assembly 170 through communication part
150 are transferred on intelligent terminal 200.Intelligent terminal 200 is also used to receive the voice signal that the transmission of wearable bracelet comes, and
After pretreatment and the characteristics extraction of completing voice signal, further progress classifier training and classifier identification, to be had
The emotional state intensity of the emotional state classification of body.It is more than default when intelligent terminal 200 recognizes Negative Emotional and emotional intensity
When threshold value, intelligent terminal 200 generates 180 enabled instruction of microcurrent stimulating component and is controlled by controller 1120 wearable
Formula bracelet starts microcurrent stimulating component 180 and works.
In one embodiment, have the impedance piece 120 there are two diameter for 3mm, impedance piece on the inner wall of bracelet main body 110
120, which obtain outer surface, successively has 320 μm of copper plate and 2 μm of Gold plated Layer, and the distance at the center of two impedance pieces 120 is
30mm.Impedance piece 120 is used to stablize the contact impedance of skin and sensor.
In one embodiment, bracelet main body 110 is flexible circuit board.EGC sensor 130, myoelectric sensor 140,
Impedance piece 120 and microcurrent stimulating component 180 are embedded in inside bracelet main body 110.Bracelet main body 110 has been internally integrated
The signal wire of EGC sensor 130, the signal wire of myoelectric sensor 140, the signal wire of microcurrent stimulating component 180 and power supply
The electric current transmission line of component 190, the signal wire of EGC sensor 130, the signal wire of myoelectric sensor 140, microcurrent stimulating group
The signal wire of part 180 and the electric current transmission line of Power Supply Assembly 190 are electrically connected with bracelet main body 110.Impedance piece 120 is distributed
On the integrated channel of 110 inner wall of bracelet main body.
In one embodiment, EGC sensor 130 includes that green luminescence LED and wavelength are corresponding with green luminescence LED
Photosensitive sensor, the wavelength 525nm of green luminescence LED, brightness are 700 luminous intensities, the sensitivity wavelength of photosensitive sensor
For 555nm.Preferably, the AM2520 patch green light that green luminescence LED can select wavelength 525nm, brightness is 700 luminous intensities
LED.It is Sharp's GA1A1S202WP ambient light sensor of 555nm that photosensitive sensor, which can select sensitivity wavelength,.
Shown in Figure 5, in one embodiment, myoelectric sensor 140 includes that array stemness electrode and myoelectricity are simulated
Acquisition Circuit, myoelectricity analog acquisition circuit include sequentially connected preposition protection circuit, primary amplifying circuit, low-pass filtering electricity
Road, high-pass filtering circuit, 50Hz power frequency notch filter, final stage amplifying circuit and level shifting circuit.The myoelectricity of wearable bracelet
Analog acquisition circuit diagram is referring to shown in attached drawing 5.
In one embodiment, voice collection assembly is built-in microphone, and voice collection assembly for acquiring spirit in real time
Voice signal around impaired patients, and transmitting voice signal collected to storage assembly 170 is saved.
In one embodiment, microcurrent stimulating component 180 includes that impulse generator and pulse current adjust circuit, pulse
Current regulating circuit is connect with the intensity for adjusting pulse current with impulse generator；When the mood that controller 1120 recognizes
When state is Negative Emotional and Negative Emotional intensity superelevation preset threshold, pulse current adjust circuit and impulse generator work with
It exports the pulse current directly proportional to the intensity of Negative Emotional and acts on the skin of patient with phychlogical problems through bracelet main body 110.
Impulse generator can produce the asymmetric long square wave of bipolarity that power frequency is 100mHz, and have 0.25 second, 0.5 second, 0.75
Second and 1 second four kinds of pulsewidth.
In one embodiment, communication part 150 has CC2640R2F chip, can use TI company CC2640R2F core
Piece is to realize the bluetooth communication based on 5.0 technical standard of bluetooth.
In one embodiment, Power Supply Assembly 190 can be solar battery.In the present embodiment, Power Supply Assembly 190 is
Transparent amorphous silicon thin-film solar cell, the top layer of Power Supply Assembly 190, as preceding electrode, are supplied using oxidic transparent conductive film
The middle layer of electrical component 190 uses PIN junction amorphous silicon membrane, and the bottom of Power Supply Assembly 190 uses oxidic transparent conductive film
As back electrode.
It in one embodiment, further include power supply management component 1130, power management component is located in accommodating cavity；Power supply pipe
It manages component and controller 1120 is electrically connected；Power management component can generate negative power supply and can be in negative power output end
Increase filter capacitor and filters out ripple to realize dual power supply.The schematic diagram of power supply management component 1130 is shown in Figure 10.
In one embodiment, 200 smart phones of intelligent terminal, tablet computer or smartwatch.
The above-mentioned monitoring of phrenoblabia convalescence mood and interfering system 10, easy to use, feature-rich, being utilized can wear
Technology, speech recognition technology are worn, the objective mood based on multi-physiological-parameter and voice signal, quantization, continuous monitoring may be implemented,
And intervened when recognizing abnormal emotion, be conducive to record the most true emotional state of patient under daily life state,
And patient with phychlogical problems's abnormal emotion is reduced or even eliminated to patient, other people and social bring harm by intervening in time.
The above-mentioned monitoring of phrenoblabia convalescence mood and interfering system 10, records patient by wearable bracelet in real time
Electrocardio, electromyography signal and voice messaging, and by extract obtain mood associated eigenvalue, obtain real-time emotion state.It is logical
The above-mentioned monitoring of phrenoblabia convalescence mood and interfering system 10 are crossed, the feelings in patient with phychlogical problems's daily life may be implemented
Thread real-time monitoring, obtains most close to the physiological signal under true emotional state, and guarantee physiological signal source in Emotion identification can
By property and accuracy.
The above-mentioned monitoring of phrenoblabia convalescence mood and interfering system 10, is separately integrated with microcurrent stimulating component 180, when
For the real-time Negative Emotional detected more than after preset threshold value, microcurrent stimulating component 180 can export pulse current, and arteries and veins
The intensity for rushing electric current is directly proportional to real-time Negative Emotional intensity, to prompt patient with phychlogical problems itself, helps its visitor
It sees ground and recognizes that the Negative Emotional of oneself is utmostly reduced because of patient with phychlogical problems not early to carry out mood adjustment
Recognize in time the Negative Emotional of oneself or can not adjust oneself Negative Emotional and to oneself, other people, social bring danger
Evil.
The above-mentioned monitoring of phrenoblabia convalescence mood and interfering system 10, realization mood real-time monitoring and Negative Emotional
Intervene in time, overcomes Traditional Spirit obstacle convalescence and need health care professional's intervention that could complete brought by motion management
Limitation, more breaching previous patient with phychlogical problems only just can be carried out convalescence motion management in related qualification hospital
Territory restriction brought by training allows more patients with phychlogical problems that can complete convalescent emotion management training, promotes health
Multiple effect.
The above-mentioned monitoring of phrenoblabia convalescence mood and interfering system 10, records electrocardio, the electromyography signal of patient in real time
And voice messaging, and handle to obtain mood associated eigenvalue by series of algorithms, it is the assessment of patient with phychlogical problems's mood
Objective quantizating index is introduced, the Subjective Factors of his evaluation table in Traditional measurements method is avoided, ensure that mood assessments
Coherence and continuity.
Above-mentioned phrenoblabia convalescence mood monitoring is monitored with interfering system 10 for phrenoblabia convalescence mood
With a kind of monitoring of phrenoblabia convalescence mood and interference method are related to when intervening.
A kind of monitoring of phrenoblabia convalescence mood includes the following steps: with interference method
EGC sensor 130 acquires the electrocardiosignal of patient with phychlogical problems, and myoelectric sensor 140 acquires patient with phychlogical problems
Electromyography signal, voice collection assembly acquire patient with phychlogical problems around voice signal.
Collected electrocardiosignal, electromyography signal are transferred to intelligent terminal by communication part 150 by controller 1120
200, the pretreatment and phase of electromyography signal are extracted with individual features value, are carried out in the pretreatment that intelligent terminal 200 carries out electrocardiosignal
Characteristics extraction, the pretreatment for carrying out voice signal and individual features value is answered to extract.
Intelligent terminal 200 obtains mood correlation by individual features value, the individual features value of electromyography signal of electrocardiosignal
Mood associated eigenvalue is compared with preset Emotion identification model for characteristic value, intelligent terminal 200, obtains real-time emotion shape
State；When real-time emotion state is Positive emotion or Negative Emotional, intelligent terminal 200 generates primary return and records instruction, intelligent terminal
The corresponding voice messaging of 200 extraction voice signals is simultaneously saved.
When the real-time emotion state detected is Negative Emotional and the Negative Emotional is more than preset threshold, intelligent terminal
200 180 enabled instructions of microcurrent stimulating component of generation simultaneously control the micro- electricity of wearable bracelet starting by controller 1120
Stream stimulation component 180 works, and microcurrent stimulating component 180 exports pulse current and prompts patient with phychlogical problems.Wherein, arteries and veins
The intensity for rushing electric current is directly proportional to the intensity of Negative Emotional.
In one embodiment, real-time emotion state is detected to judge whether the Negative Emotional is more than default after Negative Emotional
When threshold value, specifically comprise the following steps:
Intelligent terminal 200, with after corresponding characteristics extraction, carries out classifier training in the pretreatment for completing voice signal
Identify that, to obtain the emotional state intensity of real-time emotion state, intelligent terminal 200 judges that emotional state intensity is more than with classifier
Preset threshold.
In one embodiment, it obtains specifically comprising the following steps: when real-time emotion state
Intelligent terminal 200 extracts, at the signal of electromyography signal in the signal processing and individual features value for completing electrocardiosignal
After reason and individual features value are extracted, pattern classification further is carried out to electrocardiosignal and electromyography signal, to obtain real-time emotion shape
State specifically includes:
1) the feature weight value of each individual features value is initialized；
2) weight that each dimensional characteristics are calculated by Relief algorithm eliminates the lesser feature of weighted value；
3) feature vector after selection is subjected to classified calculating using classifier；
4) classification results of real-time emotion state are obtained.
Shown in Figure 8, in one embodiment, classifier training specifically includes: establishing the voice signal presorted
File set extracts characteristic parameter module for voice signal each in voice signal file set and extracts characteristic parameter, will be each
The characteristic parameter of voice signal and the label presorted put together to form the spy of a tape label for classifier modules study
Vector is levied, the feature vector for the tape label that all voice signal files are formed is put together, the feature vector of tape label is formed
Collection, using this feature vector set as training data, is trained for classifier, generates the classifier trained；
Shown in Figure 9, classifier identification specifically includes: after being successfully trained to classifier, by language to be sorted
Sound signal is input in characteristic parameter extraction module, is generated corresponding set of eigenvectors (this feature vector set not tape label), then
This set of eigenvectors is input in the classifier trained, the emotional state classification and corresponding feelings of the voice signal are generated
Not-ready status intensity.
In one embodiment, communication part 150 is with bluetooth 5.0 for technical standard and by using 2MbpsPHY:
HC1_LE_Set Default Phy Cmd indicates that controller starts PHY renewal process.
In one of the embodiments, further include following steps: intelligent terminal 200 makees the electrocardiosignal received as follows
Processing:
1) baseline drift, myoelectricity noise and the Hz noise of electrocardiosignal are removed by Butterworth filter, and are passed through
The output of Butterworth filter returns again to, and inhibits phase distortion by Butterworth filter gain；
2) characteristic point of electrocardiosignal is identified by Wavelet transformation；
It 3) include calculating when calculating the individual features value of electrocardiosignal: average value, standard deviation, first-order difference, normalization one
Order difference, second differnce, normalization second differnce, ecg-r wave wave crest, electrocardio P wave wave crest, electrocardio T wave wave crest, the interval P-Q, Q-
The interval S, the numerical value at the interval S-T, the first-order difference of adjacent P wave and T wave, QRS period, heart rate and heart rate variability numerical value.
In one of the embodiments, further include following steps: intelligent terminal 200 does the electromyography signal received as follows
Processing:
1) after electromyography signal being amplified 2000-5000 times, ambient noise, motion artifacts, interior is removed by bandpass filter
Unstability generate noise；
2) electromyography signal is sampled with the sample frequency of 1kHz, obtains the discrete value of electromyography signal；
3) by the analysis window electromyography signal that is applied to that treated；
4) include calculating when calculating the individual features value of electromyography signal in each analysis window: mean value, zero passage number,
Mean-square value, three rank moment of the origns, quadravalence moment of the orign, the mean power of power spectrum and median frequency and Wigner distribution.
In one embodiment, the voice signal around voice collection assembly acquisition patient with phychlogical problems specifically includes as follows
Step:
The voice signal around patient with phychlogical problems is acquired in real time by voice collection assembly, and voice collected is believed
Number being transmitted to memory module is saved, and memory module saves the data volume of the voice signal of 30min length, with new voice
The storage of signal, memory module delete the data volume of the voice signal before 30min length.
In one embodiment, intelligent terminal 200 extracts the corresponding voice messaging of voice signal and carries out saving specific packet
Include following steps:
When intelligent terminal 200 completes the pretreatment and the extraction of individual features value, the pre- place for completing electromyography signal of electrocardiosignal
After reason is extracted with individual features value, if obtained real-time emotion state is Positive emotion or Negative Emotional, intelligent terminal 200 is produced
Raw primary time record instruction is transmitted to Bluetooth transmission component, and the controller 1120 in wearable bracelet detects Bluetooth transmission component
When receiving back record instruction, the data volume of the voice signal of 30min stored in memory module is sent out through Bluetooth transmission component
It send to intelligent terminal 200.
In one embodiment, further include following steps:
Intelligent terminal 200 is handled the data volume of voice signal, specifically after receiving the data volume of voice signal
Include:
1) the data volume pretreatment of voice signal: including quantification treatment, preemphasis, sub-frame processing, windowing process；Voice letter
Number data volume pretreatment process figure it is shown in Figure 6.
2) it calculates voice mood characteristic value: serially the data volume of pretreated voice signal being carried out at voice signal
Reason, temporal signatures, fundamental frequency feature, voicing decision, word speed extraction, the formant for extracting the data volume of voice signal extract；Its
In, temporal signatures include short-time energy, short-time zero-crossing rate, in short-term auto-correlation coefficient and short-time average magnitade difference function；Fundamental frequency is characterized in
It is calculated by mean amplitude of tide difference function method and Cepstrum Method；Voicing decision is realized by Fisher classification；Word speed is characterized in
It is realized by the voice split plot design of wavelet transformation；Extracting formant is realized by linear predict code.Calculate voice mood
Characteristic value architecture diagram is shown in Figure 7, and temporal signatures, fundamental frequency feature, voicing decision, word speed are extracted, formant extracts difference
It is completed by temporal signatures module, fundamental frequency characteristic module, voicing decision module, word speed extraction module, formant extraction module.
Above-mentioned phrenoblabia convalescence mood monitoring and interference method, are utilized wearable technology, speech recognition technology
And machine learning techniques, the objective mood based on multi-physiological-parameter and voice signal, quantization, continuous monitoring may be implemented, and
Intervened when recognizing abnormal emotion, is conducive to record the most true emotional state of patient under daily life state, and
By intervening reduction in time or even eliminating patient with phychlogical problems's abnormal emotion to patient, other people and social bring harm.
Above-mentioned phrenoblabia convalescence mood monitoring and interference method, record patient's by wearable bracelet in real time
Electrocardiosignal, electromyography signal and voice messaging, collected electrocardiosignal, electromyography signal are transferred to intelligent terminal 200, immediately
It extracts to obtain mood associated eigenvalue by series of algorithms and be compared with Emotion identification model, obtain real-time emotion shape
State.When real-time emotion state is Positive emotion or Negative Emotional, generates primary return and record instruction, the last period automatically extracted immediately
The voice messaging of time is saved.By above-mentioned phrenoblabia convalescence mood monitoring and interference method, essence may be implemented
Mood real-time monitoring in refreshing impaired patients daily life obtains most guaranteeing feelings close to the physiological signal under true emotional state
The reliability and accuracy in physiological signal source in thread identification.Meanwhile memory can be saved by returning record instruction, and effectively record
To the relevant voice messaging of mood, accurately voice letter is provided for further fining assessment emotional intensity and disease course analysis
Breath.
Above-mentioned phrenoblabia convalescence mood monitoring and interference method, wearable bracelet are separately integrated with microcurrent stimulating
Component 180, after the real-time Negative Emotional detected is more than preset threshold, microcurrent stimulating component 180 can export pulse current,
And the intensity of pulse current is directly proportional to real-time Negative Emotional intensity, to prompt patient with phychlogical problems itself, helps
It objectively recognizes the Negative Emotional of oneself, early to carry out mood adjustment, utmostly reduces because phrenoblabia is suffered from
Person recognize the Negative Emotional of oneself not in time or the Negative Emotional of oneself can not be adjusted and to oneself, other people, society bring
Harm.
Above-mentioned phrenoblabia convalescence mood monitoring and interference method realize that mood is supervised in real time by wearable bracelet
The timely intervention with Negative Emotional is surveyed, Traditional Spirit obstacle convalescence is overcome and needs health care professional's intervention that could complete feelings
Thread manages brought limitation, and more breaching previous patient with phychlogical problems only just can be carried out in related qualification hospital
Territory restriction brought by convalescence emotion management training allows more patients with phychlogical problems that can complete convalescent mood pipe
Reason training, promotes rehabilitation efficacy.
Above-mentioned phrenoblabia convalescence mood monitoring and interference method, record patient's by wearable bracelet in real time
Electrocardiosignal, electromyography signal and voice messaging, and handle to obtain mood associated eigenvalue by series of algorithms, for spirit barrier
Hinder the assessment of patient mood to introduce objective quantizating index, avoid the Subjective Factors of his evaluation table in Traditional measurements method,
It ensure that the coherence and continuity of mood assessments.Meanwhile mood assessments are after completing quantification of targets, can be each essence
Refreshing impaired patients establish the motion management database of itself, understand patient's health convenient for patient itself, family numbers of patients and medical staff
The whole process information of emotion management training in the multiple phase provides comprehensive and accurately data information for the adjustment of subsequent rehabilitation scheme.
With the continuous accumulation of related data, it will effectively improve through electrocardiosignal, electromyography signal and voice messaging and reflect spirit
The accuracy of impaired patients real-time emotion experience.
Each technical characteristic of embodiment described above can be combined arbitrarily, for simplicity of description, not to above-mentioned reality
It applies all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, all should be considered as described in this specification.
The embodiments described above only express several embodiments of the present invention, and the description thereof is more specific and detailed, but simultaneously
Limitations on the scope of the patent of the present invention therefore cannot be interpreted as.It should be pointed out that for those of ordinary skill in the art
For, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to guarantor of the invention
Protect range.Therefore, the scope of protection of the patent of the invention shall be subject to the appended claims.
Claims (10)
1. a kind of phrenoblabia convalescence mood monitoring and interference method, which comprises the steps of:
EGC sensor acquires the electrocardiosignal of patient with phychlogical problems, and myoelectric sensor acquires the myoelectricity letter of patient with phychlogical problems
Number, voice collection assembly acquires the voice signal around patient with phychlogical problems；
Collected electrocardiosignal, electromyography signal are transferred to intelligent terminal, the intelligent terminal by communication part by controller
Carry out electrocardiosignal pretreatment and individual features value extract, carry out electromyography signal pretreatment and individual features value extraction, into
The pretreatment of row voice signal and individual features value are extracted；
The intelligent terminal obtains mood correlated characteristic by individual features value, the individual features value of electromyography signal of electrocardiosignal
The mood associated eigenvalue is compared with preset Emotion identification model for value, the intelligent terminal, obtains real-time emotion
State；
The intelligent terminal generates primary return and records instruction, and the intelligent terminal extracts the corresponding voice messaging of voice signal and carries out
It saves；
When the real-time emotion state detected is Negative Emotional and the Negative Emotional is more than preset threshold, the intelligence is eventually
End, which generates a microcurrent stimulating component enabled instruction and controls wearable bracelet by controller, starts microcurrent stimulating group
Part work, the microcurrent stimulating component output pulse current prompt patient with phychlogical problems；Wherein, pulse current is strong
It spends directly proportional to the intensity of Negative Emotional.
2. phrenoblabia convalescence mood monitoring according to claim 1 and interference method, which is characterized in that described in detection
When real-time emotion state is judges whether the Negative Emotional is more than preset threshold after Negative Emotional, specifically comprise the following steps:
The intelligent terminal complete voice signal pretreatment with after corresponding characteristics extraction, carry out classifier training and divide
The identification of class device, to obtain the emotional state intensity of the real-time emotion state, the intelligent terminal judges that the emotional state is strong
Whether degree is more than preset threshold.
3. phrenoblabia convalescence mood monitoring according to claim 2 and interference method, which is characterized in that obtain described
Specifically comprise the following steps: when real-time emotion state
The intelligent terminal extracts in the signal processing and individual features value for completing electrocardiosignal, the signal processing of electromyography signal and
After individual features value is extracted, pattern classification further is carried out to electrocardiosignal and electromyography signal, to obtain the real-time emotion shape
State specifically includes:
1) the feature weight value of each individual features value is initialized；
2) weight that each dimensional characteristics are calculated by Relief algorithm eliminates the lesser feature of weighted value；
3) feature vector after selection is subjected to classified calculating using classifier；
4) classification results of the real-time emotion state are obtained.
4. phrenoblabia convalescence mood monitoring according to claim 3 and interference method, which is characterized in that the classification
Device training specifically includes: establishing the voice signal file set presorted, and will be each in the voice signal file set
Voice signal extracts characteristic parameter, and the characteristic parameter of each voice signal is put together to be formed for classification with the label presorted
The feature vector of one tape label of device module study, the feature vector for the tape label that all voice signal files are formed is placed on
Together, the set of eigenvectors for forming tape label is trained using this feature vector set as training data for classifier, is generated
The classifier trained；
The classifier identification specifically includes: after being successfully trained to classifier, voice signal to be sorted being input to
In characteristic parameter extraction module, corresponding set of eigenvectors is generated, then this set of eigenvectors is input to the classifier trained
In, generate the emotional state classification and corresponding emotional state intensity of the voice signal.
5. phrenoblabia convalescence mood monitoring according to any one of claims 1-4 and interference method, feature exist
In the communication part is with bluetooth 5.0 for technical standard and by using 2Mbps PHY:HC1_LE_Set Default
Phy Cmd indicates that controller starts PHY renewal process.
6. phrenoblabia convalescence mood monitoring according to any one of claims 1-4 and interference method, feature exist
In further including following steps: the intelligent terminal does following processing to the electrocardiosignal received:
1) baseline drift, myoelectricity noise and the Hz noise of electrocardiosignal are removed by Butterworth filter, and by described
The output of Butterworth filter returns again to, and inhibits phase distortion by the Butterworth filter gain；
2) characteristic point of electrocardiosignal is identified by Wavelet transformation；
It 3) include calculating when calculating the individual features value of electrocardiosignal: average value, standard deviation, first-order difference, one scale of normalization
Divide, second differnce, normalization second differnce, between ecg-r wave wave crest, electrocardio P wave wave crest, electrocardio T wave wave crest, the interval P-Q, Q-S
Every, the numerical value at the interval S-T, the first-order difference of adjacent P wave and T wave, QRS period, heart rate and heart rate variability numerical value.
7. phrenoblabia convalescence mood monitoring according to any one of claims 1-4 and interference method, feature exist
In further including following steps: the intelligent terminal does following processing to the electromyography signal received:
1) after electromyography signal being amplified 2000-5000 times, ambient noise, motion artifacts, inherence are removed by bandpass filter
The noise that unstability generates；
2) electromyography signal is sampled with the sample frequency of 1kHz, obtains the discrete value of electromyography signal；
3) by the analysis window electromyography signal that is applied to that treated；
It 4) include calculating when calculating the individual features value of electromyography signal in each analysis window: mean value, zero passage number, square
Value, three rank moment of the origns, quadravalence moment of the orign, the mean power of power spectrum and median frequency and Wigner distribution.
8. phrenoblabia convalescence mood monitoring according to any one of claims 1-4 and interference method, feature exist
In the voice signal around the voice collection assembly acquisition patient with phychlogical problems specifically comprises the following steps:
The voice signal around patient with phychlogical problems is acquired in real time by voice collection assembly, and by institute's predicate collected
Sound signal is transmitted to memory module and is saved, and the memory module saves the data volume of the voice signal of 30min length,
With the storage of new voice signal, the memory module deletes the data volume of the voice signal before 30min length.
9. phrenoblabia convalescence mood monitoring according to claim 8 and interference method, which is characterized in that the intelligence
Terminal, which is extracted the corresponding voice messaging of voice signal and save, to be specifically comprised the following steps:
When the intelligent terminal complete the electrocardiosignal pretreatment and individual features value extract, complete the electromyography signal
It is described if the obtained real-time emotion state is Positive emotion or Negative Emotional after pretreatment is extracted with individual features value
Intelligent terminal generates primary time record instruction and is transmitted to communication part, and the controller in the wearable bracelet detects institute
When stating communication part and receiving back record instruction, the data volume of the voice signal of 30min stored in the memory module is passed through
The communication part is sent to the intelligent terminal.
10. phrenoblabia convalescence mood monitoring according to claim 9 and interference method, which is characterized in that further include
Following steps:
The intelligent terminal is after the data volume for receiving the voice signal, at the data volume of the voice signal
Reason, specifically includes:
1) the data volume pretreatment of the voice signal: including quantification treatment, preemphasis, sub-frame processing, windowing process；
2) it calculates voice mood characteristic value: serially the data volume of the pretreated voice signal being carried out at voice signal
Reason, temporal signatures, fundamental frequency feature, voicing decision, word speed extraction, the formant for extracting the data volume of the voice signal mention
It takes；Wherein, the temporal signatures include short-time energy, short-time zero-crossing rate, in short-term auto-correlation coefficient and short-time average magnitade difference function；Institute
Fundamental frequency is stated to be characterized in calculating by mean amplitude of tide difference function method and Cepstrum Method；The voicing decision is by Fisher classification
It realizes；The word speed is characterized in realizing by the voice split plot design of wavelet transformation；The extraction formant is to pass through linear prediction
Compiling method is realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710710278.1A CN109394203A (en) | 2017-08-18 | 2017-08-18 | The monitoring of phrenoblabia convalescence mood and interference method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710710278.1A CN109394203A (en) | 2017-08-18 | 2017-08-18 | The monitoring of phrenoblabia convalescence mood and interference method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109394203A true CN109394203A (en) | 2019-03-01 |
Family
ID=65455163
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710710278.1A Pending CN109394203A (en) | 2017-08-18 | 2017-08-18 | The monitoring of phrenoblabia convalescence mood and interference method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109394203A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110276929A (en) * | 2019-06-21 | 2019-09-24 | 西南政法大学 | A kind of intelligent remote mentally disturbed's risk early warning system based on mobile intelligent terminal |
| CN111481215A (en) * | 2020-04-09 | 2020-08-04 | 西南政法大学 | Mental disorder patient remote early warning system based on risk level judgment |
| CN113180647A (en) * | 2021-06-07 | 2021-07-30 | 郑州大学 | AI limb function rehabilitation pre-intervention behavior acquisition system and method |
| CN113616208A (en) * | 2020-05-08 | 2021-11-09 | 天津工业大学 | Emotion recognition system based on electrocardio detects |
| CN114795211A (en) * | 2022-05-18 | 2022-07-29 | 依麦(北京)国际健康管理服务有限公司 | Intelligent psychological detection and intervention training system |
| CN117316191A (en) * | 2023-11-30 | 2023-12-29 | 天津科立尔科技有限公司 | Emotion monitoring and analyzing method and system |
| CN117504142A (en) * | 2024-01-05 | 2024-02-06 | 深圳市光速时代科技有限公司 | Prompting method and system for magnetic moxibustion auxiliary fat reduction of intelligent watch |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101664304A (en) * | 2009-09-21 | 2010-03-10 | 深圳华为通信技术有限公司 | Method for healthy early warning, mobile terminal and system |
| CN103544963A (en) * | 2013-11-07 | 2014-01-29 | 东南大学 | A Speech Emotion Recognition Method Based on Kernel Semi-Supervised Discriminant Analysis |
| CN103584872A (en) * | 2013-10-29 | 2014-02-19 | 燕山大学 | A psychological stress assessment method based on the fusion of multiple physiological parameters |
| CN103932696A (en) * | 2014-04-18 | 2014-07-23 | 赵小英 | Multifunctional health status detection method and system |
| CN104010132A (en) * | 2014-05-19 | 2014-08-27 | 深圳市点通数据有限公司 | Intelligent filming device and method based on emotion control |
| CN105147248A (en) * | 2015-07-30 | 2015-12-16 | 华南理工大学 | Physiological information-based depressive disorder evaluation system and evaluation method thereof |
| CN105260745A (en) * | 2015-09-30 | 2016-01-20 | 西安沧海网络科技有限公司 | Information push service system capable of carrying out emotion recognition and prediction based on big data |
| CN105373705A (en) * | 2015-12-02 | 2016-03-02 | 广东小天才科技有限公司 | Method, device and equipment for automatically collecting life data |
| CN106027936A (en) * | 2016-07-19 | 2016-10-12 | 姚前 | Video recording method and device |
| CN106562792A (en) * | 2015-10-08 | 2017-04-19 | 松下电器（美国）知识产权公司 | Control method of information prompting device and information prompting device |
| CN106562793A (en) * | 2015-10-08 | 2017-04-19 | 松下电器（美国）知识产权公司 | Method for controlling information display apparatus, and information display apparatus |
| CN106562760A (en) * | 2015-10-12 | 2017-04-19 | 深圳迈瑞生物医疗电子股份有限公司 | Monitor and alarm control method and apparatus therefor |
| CN106683688A (en) * | 2015-11-05 | 2017-05-17 | 中国移动通信集团公司 | Emotion detection method and device |
| CN106725395A (en) * | 2017-03-22 | 2017-05-31 | 王浩宇 | Safety belt for vehicle and its method for early warning based on measurement heartbeat and respiratory rate |
| CN106725532A (en) * | 2016-12-13 | 2017-05-31 | 兰州大学 | Depression automatic evaluation system and method based on phonetic feature and machine learning |
| CN107007291A (en) * | 2017-04-05 | 2017-08-04 | 天津大学 | Recognition system and information processing method of stress intensity based on multiple physiological parameters |
| CN107025371A (en) * | 2017-03-09 | 2017-08-08 | 安徽创易心理科技有限公司 | A kind of mood is dynamically monitored and management method and system |
-
2017
- 2017-08-18 CN CN201710710278.1A patent/CN109394203A/en active Pending
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101664304A (en) * | 2009-09-21 | 2010-03-10 | 深圳华为通信技术有限公司 | Method for healthy early warning, mobile terminal and system |
| CN103584872A (en) * | 2013-10-29 | 2014-02-19 | 燕山大学 | A psychological stress assessment method based on the fusion of multiple physiological parameters |
| CN103544963A (en) * | 2013-11-07 | 2014-01-29 | 东南大学 | A Speech Emotion Recognition Method Based on Kernel Semi-Supervised Discriminant Analysis |
| CN103932696A (en) * | 2014-04-18 | 2014-07-23 | 赵小英 | Multifunctional health status detection method and system |
| CN104010132A (en) * | 2014-05-19 | 2014-08-27 | 深圳市点通数据有限公司 | Intelligent filming device and method based on emotion control |
| CN105147248A (en) * | 2015-07-30 | 2015-12-16 | 华南理工大学 | Physiological information-based depressive disorder evaluation system and evaluation method thereof |
| CN105260745A (en) * | 2015-09-30 | 2016-01-20 | 西安沧海网络科技有限公司 | Information push service system capable of carrying out emotion recognition and prediction based on big data |
| CN106562793A (en) * | 2015-10-08 | 2017-04-19 | 松下电器（美国）知识产权公司 | Method for controlling information display apparatus, and information display apparatus |
| CN106562792A (en) * | 2015-10-08 | 2017-04-19 | 松下电器（美国）知识产权公司 | Control method of information prompting device and information prompting device |
| CN106562760A (en) * | 2015-10-12 | 2017-04-19 | 深圳迈瑞生物医疗电子股份有限公司 | Monitor and alarm control method and apparatus therefor |
| CN106683688A (en) * | 2015-11-05 | 2017-05-17 | 中国移动通信集团公司 | Emotion detection method and device |
| CN105373705A (en) * | 2015-12-02 | 2016-03-02 | 广东小天才科技有限公司 | Method, device and equipment for automatically collecting life data |
| CN106027936A (en) * | 2016-07-19 | 2016-10-12 | 姚前 | Video recording method and device |
| CN106725532A (en) * | 2016-12-13 | 2017-05-31 | 兰州大学 | Depression automatic evaluation system and method based on phonetic feature and machine learning |
| CN107025371A (en) * | 2017-03-09 | 2017-08-08 | 安徽创易心理科技有限公司 | A kind of mood is dynamically monitored and management method and system |
| CN106725395A (en) * | 2017-03-22 | 2017-05-31 | 王浩宇 | Safety belt for vehicle and its method for early warning based on measurement heartbeat and respiratory rate |
| CN107007291A (en) * | 2017-04-05 | 2017-08-04 | 天津大学 | Recognition system and information processing method of stress intensity based on multiple physiological parameters |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110276929A (en) * | 2019-06-21 | 2019-09-24 | 西南政法大学 | A kind of intelligent remote mentally disturbed's risk early warning system based on mobile intelligent terminal |
| CN111481215A (en) * | 2020-04-09 | 2020-08-04 | 西南政法大学 | Mental disorder patient remote early warning system based on risk level judgment |
| CN113616208A (en) * | 2020-05-08 | 2021-11-09 | 天津工业大学 | Emotion recognition system based on electrocardio detects |
| CN113180647A (en) * | 2021-06-07 | 2021-07-30 | 郑州大学 | AI limb function rehabilitation pre-intervention behavior acquisition system and method |
| CN113180647B (en) * | 2021-06-07 | 2024-02-02 | 郑州大学 | A behavior collection system and method for AI limb function rehabilitation pre-intervention |
| CN114795211A (en) * | 2022-05-18 | 2022-07-29 | 依麦(北京)国际健康管理服务有限公司 | Intelligent psychological detection and intervention training system |
| CN117316191A (en) * | 2023-11-30 | 2023-12-29 | 天津科立尔科技有限公司 | Emotion monitoring and analyzing method and system |
| CN117504142A (en) * | 2024-01-05 | 2024-02-06 | 深圳市光速时代科技有限公司 | Prompting method and system for magnetic moxibustion auxiliary fat reduction of intelligent watch |
| CN117504142B (en) * | 2024-01-05 | 2024-03-22 | 深圳市光速时代科技有限公司 | Prompting method and system for magnetic moxibustion auxiliary fat reduction of intelligent watch |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109394203A (en) | The monitoring of phrenoblabia convalescence mood and interference method | |
| WO2020119245A1 (en) | Wearable bracelet-based emotion recognition system and method | |
| CN105147248B (en) | Depression evaluation system and evaluation method based on physiological information | |
| CN106512206B (en) | Implanted closed loop deep brain stimulation system | |
| CN105877766B (en) | A mental state detection system and method based on multi-physiological signal fusion | |
| CN107874750B (en) | Pulse rate variability and sleep quality fused psychological pressure monitoring method and device | |
| CN113855053A (en) | Wearable muscle threshold monitoring system based on myoelectricity | |
| CN113288147A (en) | Mild cognitive impairment rehabilitation evaluation system based on EEG and neurofeedback technology | |
| CN103584872A (en) | A psychological stress assessment method based on the fusion of multiple physiological parameters | |
| US11406304B2 (en) | Systems and methods for physiological sign analysis | |
| CN115640827B (en) | Intelligent closed-loop feedback network method and system for processing electrical stimulation data | |
| CN110151203A (en) | Fatigue driving recognition methods based on multistage avalanche type convolution Recursive Networks EEG analysis | |
| CN107479702A (en) | A kind of human emotion's dominance classifying identification method using EEG signals | |
| CN113288168A (en) | Wearable fatigue monitoring of intelligence and early warning system | |
| CN118044813A (en) | Mental health status assessment method and system based on multi-task learning | |
| CN114587288A (en) | A sleep monitoring method, device and device | |
| CN118885770B (en) | A method and device for identifying individual stress state based on physiological and psychological data | |
| CN106943150A (en) | Mental fatigue detecting system and its method for use | |
| CN119454052A (en) | Intelligent sleep state monitoring method and device based on brain waves | |
| CN120183674A (en) | Cognitive impairment assessment system and method based on emotional interactive multimodal physiological signals | |
| CN209203247U (en) | The wearable bracelet with intervention is monitored for phrenoblabia convalescence mood | |
| CN112057090B (en) | Wearable device and method for emotion judgment based on the characteristics of extremely low frequency potential difference on the body surface | |
| CN201227336Y (en) | Electric artificial hand controlled by brain electricity and muscle electricity | |
| CN115736864A (en) | Photoelectric sequence blood pressure monitoring method and device based on multi-head self-attention mechanism | |
| CN115607167A (en) | A lightweight model training method, atrial fibrillation detection method, device and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190301 |
|
| RJ01 | Rejection of invention patent application after publication |